# Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification

arXiv: https://arxiv.org/abs/2306.03993 · HTML: https://mlsanity.com/paper/2306.03993/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019)
- [Unsupervised Person Re-identification: Clustering and Fine-tuning](https://mlsanity.com/paper/1705.10444/) (2017)
- [Unsupervised Domain Adaptive Re-Identification: Theory and Practice](https://mlsanity.com/paper/1807.11334/) (2018)
- [Online Continual Learning under Extreme Memory Constraints](https://mlsanity.com/paper/2008.01510/) (2020)
- [Spatial-Temporal Person Re-identification](https://mlsanity.com/paper/1812.03282/) (2018)
- [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021)
- [Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification](https://mlsanity.com/paper/2101.12521/) (2021)
- [Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification](https://mlsanity.com/paper/1912.01300/) (2019)
- [SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification](https://mlsanity.com/paper/1908.09086/) (2019)
- [FlipReID: Closing the Gap between Training and Inference in Person Re-Identification](https://mlsanity.com/paper/2105.05639/) (2021)
- [Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID](https://mlsanity.com/paper/2003.06650/) (2020)
- [REVAMP2T: Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Tracking](https://mlsanity.com/paper/1911.09217/) (2019)
- [Multi-step Online Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08930/) (2020)

## Abstract (arXiv)

Following the popularity of Unsupervised Domain Adaptation (UDA) in person re-identification, the recently proposed setting of Online Unsupervised Domain Adaptation (OUDA) attempts to bridge the gap towards practical applications by introducing a consideration of streaming data. However, this still falls short of truly representing real-world applications. This paper defines the setting of Real-world Real-time Online Unsupervised Domain Adaptation (R2OUDA) for Person Re-identification. The R2OUDA setting sets the stage for true real-world real-time OUDA, bringing to light four major limitations found in real-world applications that are often neglected in current research: system generated person images, subset distribution selection, time-based data stream segmentation, and a segment-based time constraint. To address all aspects of this new R2OUDA setting, this paper further proposes Real-World Real-Time Online Streaming Mutual Mean-Teaching (R2MMT), a novel multi-camera system for real-world person re-identification. Taking a popular person re-identification dataset, R2MMT was used to construct over 100 data subsets and train more than 3000 models, exploring the breadth of the R2OUDA setting to understand the training time and accuracy trade-offs and limitations for real-world applications. R2MMT, a real-world system able to respect the strict constraints of the proposed R2OUDA setting, achieves accuracies within 0.1% of comparable OUDA methods that cannot be applied directly to real-world applications.